openai-docs
What this skill does
The skill is designed to fetch and provide current, cited OpenAI product, API, model, and Codex guidance. It includes scripts for fetching documentation from official OpenAI sources and resolving the
github/openai - Data Exfiltration - 105.1k stars
Threat analysis
Skill info
pkg:github/openai/codex@7f928f6?skill=openai-docsAssessments (2)
Data Exfiltration
Data Exfiltration via local-llm-review
scripts/fetch-codex-manual.mjs
The script fetches content from 'https://developers.openai.com/codex/codex-manual.md' and caches it locally. While this is legitimate for documentation purposes, the script does not explicitly validatConfiguration Exposure
Configuration Exposure via local-llm-review
scripts/resolve-latest-model-info.cjs
The script uses environment variables like 'LATEST_MODEL_URL' and 'LATEST_MODEL_BASE_URL' to determine the source of the model information. If these variables are not properly secured, they could be mBadge
Add the Anomity scan badge for openai-docs to your README.
How Anomity governs this at runtime
Scan-time vetting tells you what a skill says it will do. Anomity's Endpoint Sensor sees what agents actually do: it discovers skills alongside every other AI artifact on the endpoint, and runtime governance can allow, deny, or log the tool calls a skill triggers. Policy violations route to your SIEM, Slack, email, or Jira, backed by a queryable 90-day audit trail.
Book a 30-minute demo to see your own skill inventory.
Methodology and disputes
Every skill is assessed by the Anomity Skill Intelligence engine against its public source; findings indicate risk patterns, not confirmed exploitation. Maintainer of openai-docs? Report an issue or request a rescan.
